Github user HyukjinKwon commented on a diff in the pull request:
https://github.com/apache/spark/pull/21837#discussion_r204601282
--- Diff:
external/avro/src/test/scala/org/apache/spark/sql/avro/AvroSuite.scala ---
@@ -896,4 +896,33 @@ class AvroSuite extends QueryTest with
SharedSQLContext with SQLTestUtils {
assert(count == 8)
}
}
+
+ test("SPARK-24881: write with compression - avro options") {
+ withTempPath { dir =>
+ val uncompressDir = s"$dir/uncompress"
+ val deflateDir = s"$dir/deflate"
+ val snappyDir = s"$dir/snappy"
+
+ val df = spark.read.format("avro").load(testAvro)
+ df.write
+ .option("compression", "uncompressed")
+ .format("avro")
+ .save(uncompressDir)
+ df.write
+ .options(Map("compression" -> "deflate", "compressionLevel" ->
"9"))
+ .format("avro")
+ .save(deflateDir)
+ df.write
+ .option("compression", "snappy")
+ .format("avro")
+ .save(snappyDir)
+
+ val uncompressSize = FileUtils.sizeOfDirectory(new
File(uncompressDir))
+ val deflateSize = FileUtils.sizeOfDirectory(new File(deflateDir))
--- End diff --
Thank you, @MaxGekk. Can we then check the type of compression at least
`avro.codec deflate`?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
